Pinned Tweet
Big news: StackAI is joining @asana!ย
We created StackAI to empower enterprises with secure, powerful agentic workflows that automate manual processes; Asana created the operating system for human-agent teams.ย
Now, we're building the place where humans and AI agents execute across every system a business runs on.
Same product, same team, same brand, and way more fuel.
We're just getting started. ๐
StackAI retweeted
StackAI's Max Poff says dashboards have "a foot in the grave" as AI agents let users get the exact data they need without digging through static charts:
"We used to say, if you wanna work with a really convoluted Excel workbook, maybe this isn't the best fit for AI. But now, I mean, they crush it."
"One of my takes is that I think that dashboards kind of have a foot in the grave."
"Dashboards just are not that useful anymore because it captures static insights that people think will be useful to users, but then you have to slice and dice the dashboard, and even then maybe you donโt get really the insight that you want."
"With a conversational interface, you can just directly get the data you need, and then the StackAI agent maintains that data on the database layer."
@stackai
๐๐๐๐ ๐๐ต๐ถ๐ฝ๐ฝ๐ฒ๐ฑ! StackAI's Custom Analytics. Build your own dashboards to see which AI agents are working and which need attention.
Teams choose the charts and metrics that answer their own questions, instead of relying on fixed reports.
From the whole AI program to a single agent, every team can now customize their own view.
๐๐๐ข๐ ๐ฎ๐ป๐ฑ ๐๐ต๐ถ๐ฒ๐ณ ๐๐ ๐ข๐ณ๐ณ๐ถ๐ฐ๐ฒ๐ฟ๐ โ Show leadership the value, cost and reliability of the AI program in one view.
๐ฃ๐น๐ฎ๐๐ณ๐ผ๐ฟ๐บ ๐ผ๐๐ป๐ฒ๐ฟ๐ โ Find the agent that fails most and see which models drive token spend.
๐๐ด๐ฒ๐ป๐ ๐ผ๐๐ป๐ฒ๐ฟ๐ โ Track speed and errors for a specific agent, like a customer chatbot.
Built for enterprises where every team measures success differently.
Watch the quick walkthrough below. ๐
#EnterpriseAI #AgenticAI
San Diego! StackAI is hosting an executive dinner tomorrow night on how top companies use and govern AI agents.
Come meet Jonathan Kleiman, Hakan Gureren, and Omar Ashraf from StackAI to talk about:
โ How companies are automating 80%+ of back-office operations
โ Best practices for running an AI strategy
โ Which use cases to prioritize and how to measure their value
This dinner is best for CIOs, CTOs, COOs and AI leaders in finance, insurance, real estate, health care, manufacturing and construction.
๐ San Diego, CA
๐๏ธ Tuesday, November 10, 7:00pm PT
If you're in San Diego and leading AI strategy, sign up for a seat here ๐
luma.com/sandiego-ai-dinner?โฆ
#SanDiego #AgenticAI #EnterpriseAI
2
217
๐๐ฎ๐น๐น๐ถ๐ป๐ด ๐ฎ๐น๐น ๐ฟ๐ฒ๐ฎ๐น ๐ฒ๐๐๐ฎ๐๐ฒ ๐ฝ๐ฟ๐ผ๐ณ๐ฒ๐๐๐ถ๐ผ๐ป๐ฎ๐น๐: StackAI has agents for investment, brokerage, property management and REIT teams.
The agents work inside the systems you already use. ๐๐ป
๐๐ป๐๐ฒ๐๐๐บ๐ฒ๐ป๐ ๐ฎ๐ป๐ฑ ๐ฎ๐๐๐ฒ๐ ๐บ๐ฎ๐ป๐ฎ๐ด๐ฒ๐บ๐ฒ๐ป๐ โ Agents read OMs, Excel pro formas and market data and draft sourced investment memos in your template. Teams evaluate more deals and decide faster.
๐๐ฟ๐ผ๐ธ๐ฒ๐ฟ๐ฎ๐ด๐ฒ โ Pitch more listings and win more mandates with OMs, BOVs and leasing decks that agents build in Gamma or your own slide templates.
๐ฃ๐ฟ๐ผ๐ฝ๐ฒ๐ฟ๐๐ ๐บ๐ฎ๐ป๐ฎ๐ด๐ฒ๐บ๐ฒ๐ป๐ โ Agents pull 50+ cited terms from every lease, triage work orders and report arrears inside Yardi, AppFolio or MRI, so managers can handle more units with the same team.
๐ฅ๐๐๐ง๐ ๐ฎ๐ป๐ฑ ๐ฝ๐ฟ๐ผ๐ฝ๐ฒ๐ฟ๐๐ ๐ผ๐๐ป๐ฒ๐ฟ๐ โ Agents turn lease libraries in SharePoint into structured data and prepare IC-ready memos, helping teams act on deals faster and catch lease risk early.
Clients are already seeing big changes. One national property manager cut lease review time by more than 70%. One national REIT cut OM review time by 60%.
See how other real estate teams are using StackAI ๐
stackai.com/solutions/real-eโฆ
2
475
No doctor wants to fill out prior authorization forms. At Asana's Work Innovation Summit, StackAI's Max Poff and Alberto Arrighi had the room build an AI agent to do it in 30 minutes.
They built the agent in StackAI to:
1. Take in the patient's email address, an audio recording of the visit and the prior authorization form
2. Transcribe the recording with a built-in voice-to-text model
3. Write and run its own code to fill out the form
4. Email the patient a summary of the visit
Then they tested it in real time. With StackAI's VP of Healthcare, Shani Fargun, as the doctor and Max as a patient with severe abdominal pain, they recorded a visit covering his allergies, medication and diagnosis, then hit run.
A couple of minutes later, the completed form and the patient's summary email were ready.
StackAI also kept the patient data protected. We have signed agreements with every major AI model provider on how data is handled. Healthcare teams can run their agents on dedicated servers, in a private cloud or on-site, and every agent can only take the actions its builder approves.
See every agentic workflow you can run in healthcare with StackAI๐
stackai.com/solutions/healthโฆ
#AgenticAI #HealthcareAI #EnterpriseAI
3
2
262
Every AI team heading into 2027 ๐
(P.S. StackAI customers get a forward-deployed engineer and a no-code platform to turn AI pilots into real use casesโand real results ๐)
1
180
October was one for the books at StackAI. Here's everything we shipped:
โ
50+ new integrations across HR, finance, data and security tools
โ
Self-Healing Workflows, which catch quality drops and test a fix for your team to approve
โ
Sign into apps from chat. Embedded agents push account connection cards directly into conversations.
โ
Schedule Runs on any custom schedule and time zone
โ
New models, including Claude Opus 5.5 and GPT-6 Sol
See the full changelog ๐
stackai.com/changelog?utm_soโฆ
1
2
209
StackAI is heading to Fort Huachuca!
StackAI will join Dinรฉ Development Corporation at Fort Huachuca's Innovation Day, hosted by National Conference Services, Inc. (NCSI). The event brings government and industry together to match mission needs with new technology.
Stop by our exhibit to:
โ See how teams build AI agents into complex workflows
โ Securely connect agents to the systems you already use
โ Explore use cases like automating ATO documentation
โ Learn about deployment, audit-ready compliance and human controls
๐ Murr Community Center, Fort Huachuca, AZ
๐๏ธ Tuesday, November 3, 8:30am to 1:00pm MT
Details and registration in the comments. ๐
#FortHuachuca #InnovationDay #AgenticAI #GovTech
3
251
๐๐๐๐ ๐๐ต๐ถ๐ฝ๐ฝ๐ฒ๐ฑ: StackAI's Self-Healing Workflows. Higher-quality agent outputs, without hours of debugging.
Usually, when an agent fails, someone has to dig through the runs, find the cause and fix the workflow by hand.
Self-Healing Workflows take that over and turn it into a simple approval process. When an agent's quality slips, StackAI finds what went wrong, tests a fix and sends it to your team to approve in one click.
You define what the output looks like and with every run, StackAI scores the agent's result against it. When a score falls below its threshold, self-repairing starts automatically.
Then, StackAI:
1. Pulls out the failed cases and explains the cause
2. Proposes a fix in plain language
3. Tests the fix on a draft workflow, not in production, and reruns the evaluation so you can compare scores before and after
Self-Healing Workflows send suggestions automatically, but approval always stays with your team. The result is less time spent debugging and higher quality outcomes.
J.J. Miller, our product lead, gives it a quick breakdown below ๐
Learn more about StackAI's Self-Healing Workflows here --> bit.ly/4zkxoWI
45
StackAI's deployment team just got bigger. Meet the 3 newest forward deployed engineers.
๐ ๐ Yixin(Annie) Liu is based in San Francisco. She recently finished a Master's in Business Analytics at MIT, after studying Applied Mathematics and Economics at UC San Diego. She's excited to help businesses turn innovative ideas into real-world solutions.
๐ ๐ Brian Mann is based in New York. He just finished a Master's in Data Science at NYU, and before that he was a data engineer at a healthcare analytics company. Outside of work, you'll find him running, traveling and exploring NYC.
๐ ๐ Nathan Wangidjaja recently finished a Master's in Business Analytics at MIT, after studying Computer Science at Columbia University. He's excited to help businesses turn AI into tools they actually use.
Welcome to the team, Annie, Brian and Nathan!
#EnterpriseAI #AgenticAI #Hiring
1
1
261
We just hit 500+ integrations ๐
That means your AI agents can work with the systems your teams already use, like Google Drive, Notion, Slack, Asana, Airtable, Jira and AWS.
The team has been working toward this for a while, and we're excited to finally share it.
See every integration ๐
stackai.com/integrations?utmโฆ
2
1
176
Our document indexing errors dropped from ~20% to below 0.1% after we moved to Temporal Technologies.
Before an agent can use a customer's documents, our pipeline has to parse and index every file.
On our old setup, when one step failed, the retry started over from the beginning, including paid steps that had already worked.
So we moved the pipeline to Temporal incrementally. Now each stage remembers where it left off, and a retry only re-runs the step that failed.
Parsing costs are down to about a tenth of what they were. And customer complaints about indexing have stopped.
Our CTO Frank Hidalgo and AI engineer Gabriel Mermelstein wrote up how we did it ๐
stackai.com/blog/how-stackaiโฆ
2
227
Complex AI use cases donโt fail at the build stage. They fail at integration, security and deployment.
Most platforms hand you a builder and leave the rest to your team. StackAI pairs every customer with dedicated experts:
โ An AI strategist who finds use cases where agents pay off and tracks the ROI
โ A forward-deployed engineer who builds custom integrations, deploys on-premise and trains your team
โ Support in Slack, Teams or email, plus live calls when you need them
It starts with a structured proof of value: three use cases in production on the StackAI platform, running on your data and systems.
Learn more on our blog โ stackai.com/blog/stackai-givโฆ
#EnterpriseAI #AIAgents #AgenticAI
2
5
358
What if research and optimization could keep running while your team sleeps?
At @stackai, we used @OpenAI 's latest models in Codex to optimize our browser agentโwith minimal hands-on time.ย
@asana's Command tracked every run and turned the results into updates that shipped to StackAI.
๐ง๐ต๐ฒ ๐ฟ๐ฒ๐๐๐น๐: 76ร cheaper and 5ร faster in our week-long experiment.
Every night our agents aren't running feels like a wasted night.
Full story here: stackai.com/blog/how-stackaiโฆ
Introducing Custom Actions. Build the exact action your workflow needs, on the apps you already use.
StackAI's native actions cover the common operations: create a record, send a message, look up a row. But the steps that matter most, like setting a priority or applying a naming convention, are unique to how your business works, and they're usually what's missing.
Now you can build it yourself, just by describing what you need.
๐๐ผ๐ ๐ถ๐ ๐๐ผ๐ฟ๐ธ๐|ย
- ๐๐ฒ๐๐ฐ๐ฟ๐ถ๐ฏ๐ฒ ๐ถ๐: pick the app and tell the StackAI agent what the action should do. It reads the app's API docs and writes the schema and code for you.ย
- ๐ง๐ฒ๐๐ ๐ถ๐: run it against a real connection before any workflow depends on it.
- ๐ฆ๐ต๐ถ๐ฝ ๐ถ๐: it appears in the builder and every agent's tool list, right next to native actions.
๐Actions run sandboxed on connections your admins already manage, and each saved version is locked, so IT stays in control and an edit never breaks what's already running.
2
3
378
One example of what Multi-Agent Teams on @stackaiย can do: a weekly SEO report. โจ
You build one agent and ask it for the report. It works out that the job needs:
- traffic and behavior from Google Analytics
- rankings and impressions from Search Console
- backlinks and competitive position from Ahrefs
- strategy and history from a knowledge base
The agent creates a sub-agent for each, runs them in parallel, and combines the results into one report.ย
This is the simplest version of it. The same agent handles claims review, diligence, or RFP responses, and it goes well beyond a single report.
Build one agent. It executes the rest.